Model card
TextMamba.
Zhao et al.open-sourceUnknown paramsMamba (SSM) + CNN
Scene text detector using Mamba state space model for long-range dependencies. Mix-SSM block, EPEM, DSFFN components.
§ 01 · Benchmarks
Every benchmark TextMamba has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | scut-ctw1500 | Computer Vision · Optical Character Recognition | recall | 88.5% | #1 | 2024-12-09 | source ↗ |
| 02 | Total-Text | Computer Vision · Scene Text Detection | recall | 88.8% | #2 | 2024-12-09 | source ↗ |
| 03 | scut-ctw1500 | Computer Vision · Optical Character Recognition | f-measure | 89.7% | #2 | 2024-12-09 | source ↗ |
| 04 | scut-ctw1500 | Computer Vision · Optical Character Recognition | precision | 91.0% | #5 | 2024-12-09 | source ↗ |
| 05 | Total-Text | Computer Vision · Scene Text Detection | f-measure | 89.2% | #6 | 2024-12-09 | source ↗ |
| 06 | Total-Text | Computer Vision · Scene Text Detection | precision | 89.5% | #14 | 2024-12-09 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Papers
1 paper with results for TextMamba.
- 2024-12-09· Computer Vision· 6 results
TextMamba: Scene Text Detector with Mamba
§ 04 · Related models
Other Zhao et al. models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
6
results
6 of 6 rows marked verified.